SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.07112 · 2018

Improving Image Captioning with Conditional Generative Adversarial Nets

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent evaluation problem among different objective language metrics, we are motivated to design some "discriminator" networks to automatically and progressively determine whether generated caption is human described or machine generated. Two kinds of discriminator architectures (CNN and RNN-based structures) are introduced since each has its own advantages. The proposed algorithm is generic so that it can enhance any existing RL-based image captioning framework and we show that the conventional RL training method is just a special case of our approach. Empirically, we show consistent improvements over all language evaluation metrics for different state-of-the-art image captioning models. In addition, the well-trained discriminators can also be viewed as objective image captioning evaluators

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1805.07112")
get_code_for_paper("1805.07112")
have("1805.07112")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1805.07112.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1805.07112.svg)](https://syntology.ai/paper/1805.07112)

Connect an agent — have() is free.